• International Journal of Fluid Machinery and Systems
• /
• v.2 no.1
• /
• pp.1-12
• /
• 2009

Surrogate modeling is applied to a compressor blade shape optimization to modify its stacking line and thickness to enhance adiabatic efficiency and total pressure ratio. Six design variables are defined by parametric curves and three objectives; efficiency, total pressure and a combined objective of efficiency and total pressure are considered to enhance the performance of compressor blade. Latin hypercube sampling of design of experiments is used to generate 55 designs within design space constituted by the lower and upper limits of variables. Optimum designs are found by formulating a PRESS (predicted error sum of squares) based averaging (PBA) surrogate model with the help of a gradient based optimization algorithm. The optimum designs using the current variables show that, to optimize the performance of turbomachinery blade, the adiabatic efficiency objective is improved substantially while total pressure ratio objective is increased a very small amount. The multi-objective optimization shows that the efficiency can be increased with the less compensation of total pressure reduction or both objectives can be increased simultaneously.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1472-1480
• /
• 2021

Image stacking technique is one of the key techniques for complex surface reconstruction. The process includes sample collection, image processing, algorithm editing, surface reconstruction, and finally reaching reliable conclusions. Since this experiment is based on laser scanning confocal microscope to collect the original contour information of the sample, it is necessary to briefly introduce the relevant principle and operation method of laser scanning confocal microscope. After that, the original image is collected and processed, and the data is expanded by interpolation method. Meanwhile, several methods of surface reconstruction are listed. After comparing the advantages and disadvantages of each method, one-dimensional interpolation and volume rendering are finally used to reconstruct the 3D model. The experimental results show that the final 3d surface modeling is more consistent with the appearance information of the original samples. At the same time, the algorithm is simple and easy to understand, strong operability, and can meet the requirements of surface reconstruction of different types of samples.

• Computers and Concrete
• /
• v.32 no.5
• /
• pp.513-525
• /
• 2023

Recently, research on predicting the behavior of reinforced concrete (RC) columns using machine learning methods has been actively conducted. However, most studies have focused on predicting the ultimate strength of RC columns using a regression algorithm. Therefore, this study develops a successive machine learning process for predicting multiple nonlinear behaviors of rectangular RC columns. This process consists of three stages: single machine learning, bagging ensemble, and stacking ensemble. In the case of strength prediction, sufficient prediction accuracy is confirmed even in the first stage. In the case of displacement, although sufficient accuracy is not achieved in the first and second stages, the stacking ensemble model in the third stage performs better than the machine learning models in the first and second stages. In addition, the performance of the final prediction models is verified by comparing the backbone curves and hysteresis loops obtained from predicted outputs with actual experimental data.

• Advances in nano research
• /
• v.13 no.5
• /
• pp.499-512
• /
• 2022

This study investigates the efficiency of ensemble machine learning for predicting the lightweight-aggregate concrete (LWC) characteristics. A stacking ensemble (STEN) approach was proposed to estimate the dry density (DD) and 28 days compressive strength (Fc-28) of LWC using two meta-models called random forest regressor (RFR) and extra tree regressor (ETR), and two novel ensemble models called STEN-RFR and STEN-ETR, were constructed. Four standalone machine learning models including artificial neural network, gradient boosting regression, K neighbor regression, and support vector regression were used to compare the performance of the proposed models. For this purpose, a sum of 140 LWC mixtures with 21 influencing parameters for producing LWC with a density less than 1000 kg/m³, were used. Based on the experimental results with multiple performance criteria, it can be concluded that the proposed STEN-ETR model can be used to estimate the DD and Fc-28 of LWC. Moreover, the STEN-ETR approach was found to be a significant technique in prediction DD and Fc-28 of LWC with minimal prediction error. In the validation phase, the accuracy of the proposed STEN-ETR model in predicting DD and Fc-28 was found to be 96.79% and 81.50%, respectively. In addition, the significance of cement, water-cement ratio, silica fume, and aggregate with expanded glass variables is efficient in modeling DD and Fc-28 of LWC.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.27 no.6
• /
• pp.321-330
• /
• 2023

In this study, the structural performance of the specimen fabricated through 3D printing was evaluated through monotonic loading experiments analysis to apply to 3D printed structures. The compression and flexural experiments were carried out, and the experimental results were compared to the finite element model results. The loading directions of specimens were investigated to consider the capacity of specimens with different curing periods, such as 7 and 28 days. As a result, the strength tended to increase slightly depending on the stacking direction. Also, between the 3D-printed panel composite and the non-reinforced panel, the bending performance depended on the presence or absence of composite reinforcement.

• Proceeding of KASS Symposium
• /
• 2008.05a
• /
• pp.113-118
• /
• 2008

This paper presents a flexural-torsional analysis of thin-walled open-section composite beams. A general geometrically nonlinear model for thin-walled composite beams and general laminate stacking sequences is given by using systematic variational formulation based on the classical lamination theory. The nonlinear algebraic equations of present theory are linearized and solved by means of an incremental Newton-Raphson method. Based on the analytical model, a displacement-based one-dimensional finite element model is developed to formulate the problem. Numerical results are obtained for thin-walled composite beams under general loadings, addressing the effects of fiber angle, laminate stacking sequence and loading parameters.

• Steel and Composite Structures
• /
• v.25 no.1
• /
• pp.105-116
• /
• 2017

This paper presents the dynamic stability study of laminated composite plates with different force combinations and aspect ratios. Optimum non-diverging stacking is obtained for certain loading combination and aspect ratio. In addition, the stability force is maximized for a definite operating frequency. A dynamic version of the principle of virtual work for laminated composites is used to obtain force-frequency relation. Since dynamic stiffness governs the divergence or flutter, an efficient optimization method is necessary for the response functional and the relevant constraints. In this way, a model based on the ant colony optimization (ACO) algorithm is proposed to search for the proper stacking. The ACO algorithm is used since it treats with large number of dynamic stability parameters. Governing equations are formulated using classic laminate theory (CLT) and von-Karman plate technique. Load-frequency relations are explicitly obtained for fundamental and secondary flutter modes of simply supported composite plate with arbitrary aspect ratio, stacking and boundary load, which are used in optimization process. Obtained results are compared with the finite element method results for validity and accuracy convince. Results revealed that the optimum stacking with stable dynamic response and maximum critical load is in angle-ply mode with almost near-unidirectional fiber orientations for fundamental flutter mode. In addition, short plates behave better than long plates in combined axial-shear load case regarding stable oscillation. The interaction of uniaxial and shear forces intensifies the instability in long plates than short ones which needs low-angle layup orientations to provide required dynamic stiffness. However, a combination of angle-ply and cross-ply stacking with a near-square aspect ratio is appropriate for the composite plate regarding secondary flutter mode.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2001.10a
• /
• pp.183-186
• /
• 2001

In this paper, the analytical model to understand the propagation of electromagnetic waves in the foam core sandwich structures was proposed. Using the analytical model, efforts were made to find the optimal stacking sequence of composite skins for maximum transmittance of electromagnetic wave. Numerical analyses of unidirectional composites and foam as a function of incident angle were performed. From the results of analysis, the general tendencies of transmittance of electromagnetic wave through composites and foam were obtained. Based on the general tendencies, optimal stacking sequences of composite skins for the maximum transmittance of electromagnetic wave were found with certain ranges of incident angle using genetic algorithm(GA).

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.420-423
• /
• 2008

This present work is to find optimum design of a NACA65 axial fan blade with weighted average surrogate model. The numerical analysis by Reynolds-average Navier-Stokes equations with shear stress turbulence(SST) is discretized by finite volume approximations and solved on hexahedral grids for flow analysis. The blade aerodynamic shape is modified by six design variables for the optimization. The blade profile as well as stacking line is modified to enhance blade total efficiency. Six design variables, airfoil maximum camber, maximum camber location, leading edge radius, trailing edge radius, lean angle at 50% span and lean angle at 100% span, are selected for blade profile to enhance the total efficiency. The PBA model which is basically weighted average of the basis surrogates is used to find the optimal design in the design space from the constructed response surface model for the objective function. By the optimization, the total efficiency is increased by 1.4%.